US20040230771A1 - Reconfigurable signal processing IC with an embedded flash memory device - Google Patents
Reconfigurable signal processing IC with an embedded flash memory device Download PDFInfo
- Publication number
- US20040230771A1 US20040230771A1 US10/768,401 US76840104A US2004230771A1 US 20040230771 A1 US20040230771 A1 US 20040230771A1 US 76840104 A US76840104 A US 76840104A US 2004230771 A1 US2004230771 A1 US 2004230771A1
- Authority
- US
- United States
- Prior art keywords
- fpga
- embedded
- flash memory
- port
- processing unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F15/00—Digital computers in general; Data processing equipment in general
- G06F15/76—Architectures of general purpose stored program computers
- G06F15/78—Architectures of general purpose stored program computers comprising a single central processing unit
- G06F15/7867—Architectures of general purpose stored program computers comprising a single central processing unit with reconfigurable architecture
-
- G—PHYSICS
- G11—INFORMATION STORAGE
- G11C—STATIC STORES
- G11C16/00—Erasable programmable read-only memories
- G11C16/02—Erasable programmable read-only memories electrically programmable
- G11C16/06—Auxiliary circuits, e.g. for writing into memory
- G11C16/30—Power supply circuits
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Definitions
- the present invention relates to dynamically reconfigurable processing units connected to a Flash EEPROM memory subsystem. More specifically, the present invention relates to a reconfigurable signal processing integrated circuit with an embedded Flash memory device for non-volatile storage of code, data and bit-streams.
- the unit is integrated into a single chip together with a microprocessor core.
- FPGA Field Programmable Gate Array
- the existing models for designing FPGA/processor interaction can be grouped in two main categories: 1) the FPGA is a co-processor communicating with the main processor through a system bus or a specific I/O channel; and 2) the FPGA is described as a function unit of the processor pipeline.
- the first group includes the GARP processor, known from the article by T. Callahan, J. Hauser, and J. Wawrzynek, “The Garp Architecture And C Compiler” IEEE Computer, 33(4): 62-69, April 2000.
- a similar architecture is provided by the A-EPIC processor that is disclosed in the article by S. Palem and S. Talla, “Adaptive Explicit Parallel Instruction Computing”, Proceedings of the fourth Australian Computer Architecture Conference (ACOAC), January 2001.
- FPGA suppliers such as Altera Corporation offer digital architectures based on U.S. Pat. No. 5,968,161 to T. J. Southgate, “FPGA Based Configurable CPU Additionally Including Second Programmable Section For Implementation Of Custom Hardware Support”.
- Other suppliers Xilinx, Triscend
- chips containing a processor embedded on the same silicon IC with embedded FPGA logic See for instance U.S. Pat. No. 6,467,009 to S. P. Winegarden et al., “Configurable Processor System Unit”, assigned to Triscend Corporation.
- An object of the present invention is to provide a reconfigurable processing unit that is connected to a memory architecture having functional and structural features offering significant performance and power consumption enhancements with respect to a traditional signal processing device.
- the invention overcomes the limitations of similar preceding architectures relying on an embedded device of a different nature, and this is based upon a new approach to processor/memory interface.
- the reconfigurable processing unit targets image-voice processing and recognition application domains by joining a configurable and extensible processor core and an SRAM-based embedded FPGA.
- the processing unit may includes an S-RAM based embedded FPGA unit structured for FPGA reconfigurations having a specific programming interface connected to a port FA of the Flash memory device through a direct memory access (DMA) channel.
- DMA direct memory access
- FIG. 1 is a block diagram of a processing unit architecture for data processing according to the present invention
- FIG. 2 is a block diagram of a Flash memory architecture embedded into the processing unit of FIG. 1;
- FIG. 3 is a schematic view of a system memory hierarchy provided by the present invention.
- FIG. 4 is a block diagram of a specific processor extension according to the present invention with respect to added DSP instruction examples
- FIG. 5 is a block diagram of a further specific processor extension according to the present invention with respect to an optimized fixed-point calculation of the square root accounts;
- FIG. 6 is a table view showing the overall performance improvements for a face recognition task implemented by the processing unit of the present invention.
- FIG. 7 is a schematic chip micrograph according to the present invention.
- the processing unit 1 includes an embedded Flash memory 4 for non-volatile storage of code, data and bit-streams, and an additional S-RAM based embedded FPGA 3 formed for the configuration purposes of the present invention. More specifically, an 8 Mb application-specific embedded flash memory 4 is disclosed.
- the memory 4 is integrated into a single chip together with a microprocessor 2 and the FPGA structure 3 .
- application-specific hardware units are added and dynamically modified by the embedded FPGA 3 reconfiguration.
- the processing unit 1 shows a peak computing power of 1 GOPS.
- Flash memory 4 Efficient read-write-erase access to code, data and FPGA bitstreams is provided by the Flash memory 4 based on a modular 8 Mb, 4-bank Flash memory, as will be more clearly explained below.
- the processing unit 1 comprises three content-specific I/O ports and delivers an aggregate peak read throughput of 1.2 GB/s.
- the system architecture 1 is illustrated in FIG. 1.
- the functional purposes of the embedded FPGA 3 are as follows: i) extension of the processor datapath supporting a set of additional special purpose C-callable microprocessor instructions; ii) bus-mapped coprocessors connected to the system bus through a master/slave interface; and iii) flexible I/O to connect external units or sensors with application-specific communication protocols.
- the single, high I/O count, fine-grain e-FPGA 3 operates as a datapath for the microprocessor pipeline and as dedicated control logic for bus coprocessor and I/O control interface.
- the FPGA has a specific programming interface 7 connected to a port FP of said Flash memory device 4 through a DMA channel 8 .
- FPGA reconfiguration is concurrent with software execution.
- a local bus 6 connects a dedicated 32-bit Flash memory port FP to the FPGA programming interface 7 .
- a DMA channel 8 handles the bitstream transfer while the microprocessor 2 fetches instructions and data from different Flash memory ports: 64-bit wide code port (CP) and data port (DP).
- CP 64-bit wide code port
- DP data port
- a 1 kB dual-port buffer 9 is used to interface fast decoding hardware and slower software running on the processor 2 .
- the memory sub-system architecture is shown in FIG. 2.
- the modular structure of the memory includes: charge pumps 10 (Power Block), testability circuits 11 (DFT), a power management arbiter 12 (PMA), and a customizable array 13 of N independent 2 Mb flash memory modules 16 .
- charge pumps 10 Power Block
- DFT testability circuits 11
- PMA power management arbiter 12
- N customizable array 13 of N independent 2 Mb flash memory modules 16 .
- the modular memory features (N+2) 128-bit target ports and implements an N-bank uniform memory 13 .
- three content-specific ports are dedicated to code (CP, 64-bit wide), data (DP, 64-bit) and FPGA bit stream configurations (FP, 32-bit).
- a 128 bit sub-system crossbar 15 connects all the architecture blocks and the eight bit microprocessor 2 .
- the main features of the flash memory device 4 includes a charge pump 10 sharing among different flash memory modules 16 through the PMA arbiter 12 in a multi-bank fashion. Moreover, the use of a small eight bit microprocessor 2 allows easy memory system test and adds complex functionalities for data management, and the use of an ADC (Analog-to-Digital Converter), required by the application, increase system self-test capability.
- ADC Analog-to-Digital Converter
- the third FP port of the Flash device 4 is dedicated to manage embedded-FPGA (e-FPGA) configurations data stored in flash memory modules.
- the FP port is read-only and provides fast sequential access for bit stream downloading.
- the FP has four configuration registers replicating the information stored in CP port that must be used to write e-FPGA configurations data.
- the output data word bus and the address bus are 32 bits wide.
- the FP port uses a chip select to access in the addressable memory space, and a burst enable to allow burst serial access. In a read operation, an output ready signal is tied low when data is not immediately available, so that it can act as a wait state signal.
- the eight-bit microprocessor 2 performs additional complex functions (defragmentation, compression, virtual erase, etc.) not natively supported by the DP port, and assists for built-in self-test of the memory system.
- the (N+2) ⁇ 4 128-bit crossbar 15 connects the modular memory with the four initiators (CP, DP, FP and uP) providing that at least three flash memory modules 16 can be read in parallel at full speed.
- the memory space of the four modules 16 is arranged in three programmable user-defined partitions, each one devoted to a port.
- the memory system clock can run up to 100 MHz, and reading three modules 16 with a 128 bit data bus and 40 ns access time results in a peak read throughput of 1.2 GB/s.
- Each 2 Mb flash memory module 16 has a 128-bit IO data bus with 40 ns access time, resulting in 400 Mbyte/s, and a program/erase control unit. Simultaneous memory operations use the power management arbiter 12 (PMA) for optimal scheduling.
- PMA power management arbiter 12
- the memory device 4 allows up to four simultaneous operations, with a limit of one both for write and erase.
- FIG. 3 depicts the memory hierarchy and its parallel architecture across the processing unit 1 .
- the ports CP and DP are interfaced to the 64-bit, 800 MB/s AHB system bus 6 .
- each I/O port can independently operate at maximum speed.
- An aggregate peak read rate of 1.2 GB/s can thus be sustained as it is limited by memory access time.
- the e-FPGA reconfiguration takes 500 ⁇ s at 100 MHz. 50 MB/s average throughput out of the available 400 MB/s are currently sustained by the e-FPGA configuration interface 7 .
- FIGS. 4 and 5 show two examples of specific microprocessor extensions.
- FIG. 4 relates to an eight-issue, eight-bit, L2 calculation accounts for 23 eight-bit arithmetic operations and six 64-bit operations requiring about 10 k ASIC equivalent gates.
- FIG. 5 relates to a datapath for an optimized fixed-point calculation of the square root accounts for twelve 32-bit operations for about 2 k ASIC equivalent gates. The overall performance improvements for the face recognition tasks are shown in FIG. 6.
- Execution time is compared for a 32-bit RISC with basic DSP extensions (MAC, zero-overhead loops, etc) and the same processor enhanced with application-specific instructions. Measured speed-ups range from 1.8 ⁇ to 10.6 ⁇ (on the most-demanding task), with an overall improvement of 8.5 ⁇ . Switching between algorithm stages requires only one reconfiguration of the e-FPGA. Reconfiguration time is negligible.
- the full-processing unit on a single chip is implemented in a 0.18 ⁇ m, 2 PL-6 ML CMOS embedded Flash technology. Chip area is 70 mm 2 , and the technology and device characteristics are summarized in FIG. 6. A chip micrograph is shown in FIG. 7.
Abstract
Description
- The present invention relates to dynamically reconfigurable processing units connected to a Flash EEPROM memory subsystem. More specifically, the present invention relates to a reconfigurable signal processing integrated circuit with an embedded Flash memory device for non-volatile storage of code, data and bit-streams. The unit is integrated into a single chip together with a microprocessor core.
- Increasing complexity of system design and shorter time-to-market requirements are leading research towards the investigation of hybrid systems including processors enhanced by programmable logic as readily known by those skilled in this technical field. In this respect, reference is made to the work by Young-Don Bae et al., “A Single-Chip Programmable Platform Base on A Multithreaded Processor and Configurable Logic Clusters”, ISSCC 2002 Digest of Technical Papers, pp 336-337, February 2002. Moreover, a further reference which may be considered is an article by Zhang et al., “A 1V Heterogeneous Reconfigurable Processor IC for Baseband Wireless Applications”, ISSCC 2000 Digest of Technical Papers, pp 68-69,488, February 2000.
- At the same time increased costs of mask sets and a shorter time-to-market available for new products are leading to the introduction of systems with a higher degree of programmability and configurability, such as system-on-chips with configurable processors, embedded FPGA and embedded flash memory. Moreover, the availability of an advanced embedded flash technology, based on a NOR architecture, together with innovative IP's, like embedded flash macrocells with special features, is a key factor.
- For a better understanding of the present invention reference is also made to the Field Programmable Gate Array (FPGA) technology combining standard processors with embedded FPGA devices. These approaches allow one to configure into the FPGA at deployment time exactly the required peripherals, exploiting temporal reuse by dynamically reconfiguring the instruction set at run time based on the currently executed algorithm.
- The existing models for designing FPGA/processor interaction can be grouped in two main categories: 1) the FPGA is a co-processor communicating with the main processor through a system bus or a specific I/O channel; and 2) the FPGA is described as a function unit of the processor pipeline. The first group includes the GARP processor, known from the article by T. Callahan, J. Hauser, and J. Wawrzynek, “The Garp Architecture And C Compiler” IEEE Computer, 33(4): 62-69, April 2000. A similar architecture is provided by the A-EPIC processor that is disclosed in the article by S. Palem and S. Talla, “Adaptive Explicit Parallel Instruction Computing”, Proceedings of the fourth Australian Computer Architecture Conference (ACOAC), January 2001.
- In both cases the FPGA is addressed via dedicated instructions, moving data explicitly to and from the processor. Control hardware is kept to a minimum since no interlocks are needed to avoid hazards, but a significant overhead in clock cycles is required to implement communication. When the number of cycles per execution of the FPGA is relatively high, the communication overhead may be considered negligible.
- In the commercial world, FPGA suppliers such as Altera Corporation offer digital architectures based on U.S. Pat. No. 5,968,161 to T. J. Southgate, “FPGA Based Configurable CPU Additionally Including Second Programmable Section For Implementation Of Custom Hardware Support”. Other suppliers (Xilinx, Triscend) offer chips containing a processor embedded on the same silicon IC with embedded FPGA logic. See for instance U.S. Pat. No. 6,467,009 to S. P. Winegarden et al., “Configurable Processor System Unit”, assigned to Triscend Corporation.
- However, those chips are generally loosely coupled by a high speed dedicated bus, performing as two separate execution units rather than being merged in a single architectural entity. In this manner the FPGA does not have direct access to the processor memory subsystem, which is one of the strengths of academic approaches outlined above. In the second category (FPGA as a function unit) we find architectures commercially known as PRISC, Chimaera and ConCISe.
- In all these models, data is read and written directly on the processor register file minimizing overhead due to communication. In most cases, to minimize control logic and hazard handling and to fit in the processor pipeline stages, the FPGA is limited to combinatorial logic only. This severely limits the performance boost that can be achieved.
- These approaches represent a significant step toward a low-overhead interface between the two entities. Nevertheless, due to the granularity of FPGA operations and its hardware oriented structure, their approach is still very coarse-grained, reducing the possible resource usage in parallel and again including hardware issues not familiar nor friendly to software compilation tools and algorithm developers.
- Thus, a relevant drawback in this approach is often the memory data access bottleneck that often forces long stalls on the FPGA device when fetching on the shared registers enough data to justify its activation.
- An object of the present invention is to provide a reconfigurable processing unit that is connected to a memory architecture having functional and structural features offering significant performance and power consumption enhancements with respect to a traditional signal processing device.
- The invention overcomes the limitations of similar preceding architectures relying on an embedded device of a different nature, and this is based upon a new approach to processor/memory interface. According to a first embodiment of the present invention, the reconfigurable processing unit targets image-voice processing and recognition application domains by joining a configurable and extensible processor core and an SRAM-based embedded FPGA.
- More specifically, the processing unit according to the invention may includes an S-RAM based embedded FPGA unit structured for FPGA reconfigurations having a specific programming interface connected to a port FA of the Flash memory device through a direct memory access (DMA) channel.
- The features and advantages of the processing unit according to the present invention will become apparent from the following description of a best mode for carrying out the invention given by way of a non-limiting example with reference to the enclosed drawings.
- FIG. 1 is a block diagram of a processing unit architecture for data processing according to the present invention;
- FIG. 2 is a block diagram of a Flash memory architecture embedded into the processing unit of FIG. 1;
- FIG. 3 is a schematic view of a system memory hierarchy provided by the present invention;
- FIG. 4 is a block diagram of a specific processor extension according to the present invention with respect to added DSP instruction examples;
- FIG. 5 is a block diagram of a further specific processor extension according to the present invention with respect to an optimized fixed-point calculation of the square root accounts;
- FIG. 6 is a table view showing the overall performance improvements for a face recognition task implemented by the processing unit of the present invention; and
- FIG. 7 is a schematic chip micrograph according to the present invention.
- With reference to the drawings, generally shown at 1 is a processing unit formed according to the present invention for digital signal processing based on reconfigurable computing. The
processing unit 1 includes an embedded Flashmemory 4 for non-volatile storage of code, data and bit-streams, and an additional S-RAM based embeddedFPGA 3 formed for the configuration purposes of the present invention. More specifically, an 8 Mb application-specific embeddedflash memory 4 is disclosed. Thememory 4 is integrated into a single chip together with amicroprocessor 2 and theFPGA structure 3. - Advantageously, application-specific hardware units are added and dynamically modified by the embedded
FPGA 3 reconfiguration. By implementing application-specific vector processing instructions theprocessing unit 1 shows a peak computing power of 1 GOPS. - Efficient read-write-erase access to code, data and FPGA bitstreams is provided by the Flash
memory 4 based on a modular 8 Mb, 4-bank Flash memory, as will be more clearly explained below. - The
processing unit 1 comprises three content-specific I/O ports and delivers an aggregate peak read throughput of 1.2 GB/s. Thesystem architecture 1 is illustrated in FIG. 1. The functional purposes of the embeddedFPGA 3 are as follows: i) extension of the processor datapath supporting a set of additional special purpose C-callable microprocessor instructions; ii) bus-mapped coprocessors connected to the system bus through a master/slave interface; and iii) flexible I/O to connect external units or sensors with application-specific communication protocols. - Even though such different circuit purposes would require different kinds of programmable logic for best implementation of either arithmetic-dominated or control-dominated logic, a single
programmable logic subsystem 3 has been implemented to be shared among different purposes both in space (same configuration) and time (subsequent configurations). - The single, high I/O count, fine-
grain e-FPGA 3 operates as a datapath for the microprocessor pipeline and as dedicated control logic for bus coprocessor and I/O control interface. The FPGA has a specific programming interface 7 connected to a port FP of said Flashmemory device 4 through aDMA channel 8. FPGA reconfiguration is concurrent with software execution. - A
local bus 6 connects a dedicated 32-bit Flash memory port FP to the FPGA programming interface 7. ADMA channel 8 handles the bitstream transfer while themicroprocessor 2 fetches instructions and data from different Flash memory ports: 64-bit wide code port (CP) and data port (DP). To support streaming applications a 1 kB dual-port buffer 9 is used to interface fast decoding hardware and slower software running on theprocessor 2. The memory sub-system architecture is shown in FIG. 2. - The modular structure of the memory (dotted line) includes: charge pumps10 (Power Block), testability circuits 11 (DFT), a power management arbiter 12 (PMA), and a
customizable array 13 of N independent 2 Mbflash memory modules 16. Depending on the storage requirements the number N may be chosen with N=4 in the current implementation. - The modular memory features (N+2) 128-bit target ports and implements an N-
bank uniform memory 13. As previously mentioned, three content-specific ports are dedicated to code (CP, 64-bit wide), data (DP, 64-bit) and FPGA bit stream configurations (FP, 32-bit). A 128 bitsub-system crossbar 15 connects all the architecture blocks and the eightbit microprocessor 2. - The main features of the
flash memory device 4 includes acharge pump 10 sharing among differentflash memory modules 16 through thePMA arbiter 12 in a multi-bank fashion. Moreover, the use of a small eightbit microprocessor 2 allows easy memory system test and adds complex functionalities for data management, and the use of an ADC (Analog-to-Digital Converter), required by the application, increase system self-test capability. - The third FP port of the
Flash device 4 is dedicated to manage embedded-FPGA (e-FPGA) configurations data stored in flash memory modules. The FP port is read-only and provides fast sequential access for bit stream downloading. The FP has four configuration registers replicating the information stored in CP port that must be used to write e-FPGA configurations data. - The output data word bus and the address bus are 32 bits wide. The FP port uses a chip select to access in the addressable memory space, and a burst enable to allow burst serial access. In a read operation, an output ready signal is tied low when data is not immediately available, so that it can act as a wait state signal.
- The eight-bit microprocessor2 (uP) performs additional complex functions (defragmentation, compression, virtual erase, etc.) not natively supported by the DP port, and assists for built-in self-test of the memory system. The (N+2)×4 128-
bit crossbar 15 connects the modular memory with the four initiators (CP, DP, FP and uP) providing that at least threeflash memory modules 16 can be read in parallel at full speed. - The memory space of the four
modules 16 is arranged in three programmable user-defined partitions, each one devoted to a port. The memory system clock can run up to 100 MHz, and reading threemodules 16 with a 128 bit data bus and 40 ns access time results in a peak read throughput of 1.2 GB/s. Each 2 Mbflash memory module 16 has a 128-bit IO data bus with 40 ns access time, resulting in 400 Mbyte/s, and a program/erase control unit. Simultaneous memory operations use the power management arbiter 12 (PMA) for optimal scheduling. - Available power and user-defined priorities are considered to schedule conflicting resource requests in a single clock cycle. The
memory device 4 allows up to four simultaneous operations, with a limit of one both for write and erase. - FIG. 3 depicts the memory hierarchy and its parallel architecture across the
processing unit 1. The ports CP and DP are interfaced to the 64-bit, 800 MB/sAHB system bus 6. At a system clock rate of 100 MHz each I/O port can independently operate at maximum speed. An aggregate peak read rate of 1.2 GB/s can thus be sustained as it is limited by memory access time. In the current implementation, the e-FPGA reconfiguration takes 500 μs at 100 MHz. 50 MB/s average throughput out of the available 400 MB/s are currently sustained by the e-FPGA configuration interface 7. - System performance was evaluated for an image processing application (facial recognition) and a speech recognition application. More than 20 specific instructions were designed as C/assembly-callable functions, automatically translated to RTL, then synthesized and mapped to the e-FPGA.
- FIGS. 4 and 5 show two examples of specific microprocessor extensions. FIG. 4 relates to an eight-issue, eight-bit, L2 calculation accounts for 23 eight-bit arithmetic operations and six 64-bit operations requiring about 10 k ASIC equivalent gates.
- FIG. 5 relates to a datapath for an optimized fixed-point calculation of the square root accounts for twelve 32-bit operations for about 2 k ASIC equivalent gates. The overall performance improvements for the face recognition tasks are shown in FIG. 6.
- Execution time is compared for a 32-bit RISC with basic DSP extensions (MAC, zero-overhead loops, etc) and the same processor enhanced with application-specific instructions. Measured speed-ups range from 1.8×to 10.6×(on the most-demanding task), with an overall improvement of 8.5×. Switching between algorithm stages requires only one reconfiguration of the e-FPGA. Reconfiguration time is negligible.
- The speed-up factors take into account the possible multi-cycle clock penalty due to processor-FPGA synchronization in case of instruction extensions slower than the processor clock. Energy efficiency figures are reported in FIG. 6 also.
- As the average power consumption of the system extended with the e-FPGA is slightly higher (10-15%), the energy reduction for executing each of the tasks on its specific HW configuration (power-delay product improvement) results in an overall reduction of 6.7×. Only one task showed slightly worse total execution energy, though showing benefits on execution speed.
- The last column of FIG. 6 reports the power-delay improvement of each specific HW configuration compared to the general-purpose counterpart. Energy required for e-FPGA reconfiguration is always negligible. Measurements show the best energy efficiency in the range of several MOPS/mW at 1.8V supply. It lies between conventional ASIP/DSP and dedicated configurable hardware implementations.
- The full-processing unit on a single chip is implemented in a 0.18 μm, 2 PL-6 ML CMOS embedded Flash technology. Chip area is 70 mm2, and the technology and device characteristics are summarized in FIG. 6. A chip micrograph is shown in FIG. 7.
Claims (28)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP03425054A EP1443417A1 (en) | 2003-01-31 | 2003-01-31 | A reconfigurable signal processor with embedded flash memory device |
EP03425054.8 | 2003-01-31 |
Publications (2)
Publication Number | Publication Date |
---|---|
US20040230771A1 true US20040230771A1 (en) | 2004-11-18 |
US7360068B2 US7360068B2 (en) | 2008-04-15 |
Family
ID=32605500
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US10/768,401 Active 2025-03-15 US7360068B2 (en) | 2003-01-31 | 2004-01-30 | Reconfigurable signal processing IC with an embedded flash memory device |
Country Status (2)
Country | Link |
---|---|
US (1) | US7360068B2 (en) |
EP (1) | EP1443417A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008004158A1 (en) * | 2006-07-03 | 2008-01-10 | Nxp B.V. | Method and system for configuration of a hardware peripheral |
US20120004860A1 (en) * | 2010-07-05 | 2012-01-05 | Endress + Hauser Gmbh + Co. Kg | Field device for determining or monitoring a physical or chemical, process variable |
WO2012118586A1 (en) * | 2011-02-28 | 2012-09-07 | Xilinx, Inc. | Integrated circuit with programmable circuitry and an embedded processor system |
US8612789B2 (en) | 2011-01-13 | 2013-12-17 | Xilinx, Inc. | Power management within an integrated circuit |
CN106648507A (en) * | 2016-12-05 | 2017-05-10 | 中国航空工业集团公司洛阳电光设备研究所 | Circuit and method used for extended DVI display output of embedded processor |
US10963268B1 (en) | 2017-04-18 | 2021-03-30 | Amazon Technologies, Inc. | Interception of identifier indicative of client configurable hardware logic and configuration data |
US11226914B2 (en) * | 2017-09-14 | 2022-01-18 | Samsung Electronics Co., Ltd. | Heterogeneous accelerator for highly efficient learning systems |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7613900B2 (en) | 2003-03-31 | 2009-11-03 | Stretch, Inc. | Systems and methods for selecting input/output configuration in an integrated circuit |
US7590829B2 (en) | 2003-03-31 | 2009-09-15 | Stretch, Inc. | Extension adapter |
US7581081B2 (en) | 2003-03-31 | 2009-08-25 | Stretch, Inc. | Systems and methods for software extensible multi-processing |
US8001266B1 (en) | 2003-03-31 | 2011-08-16 | Stretch, Inc. | Configuring a multi-processor system |
US7418575B2 (en) | 2003-07-29 | 2008-08-26 | Stretch, Inc. | Long instruction word processing with instruction extensions |
US7373642B2 (en) | 2003-07-29 | 2008-05-13 | Stretch, Inc. | Defining instruction extensions in a standard programming language |
EP1713007B1 (en) * | 2005-04-11 | 2008-09-17 | STMicroelectronics S.r.l. | A dynamically reconfigurable System-on-Chip comprising a plurality of reconfigurable gate array devices |
US7382154B2 (en) | 2005-10-03 | 2008-06-03 | Honeywell International Inc. | Reconfigurable network on a chip |
US7616508B1 (en) * | 2006-08-10 | 2009-11-10 | Actel Corporation | Flash-based FPGA with secure reprogramming |
US8639510B1 (en) | 2007-12-24 | 2014-01-28 | Kai Yu | Acoustic scoring unit implemented on a single FPGA or ASIC |
US8352265B1 (en) | 2007-12-24 | 2013-01-08 | Edward Lin | Hardware implemented backend search engine for a high-rate speech recognition system |
US8463610B1 (en) | 2008-01-18 | 2013-06-11 | Patrick J. Bourke | Hardware-implemented scalable modular engine for low-power speech recognition |
US8055936B2 (en) * | 2008-12-31 | 2011-11-08 | Pitney Bowes Inc. | System and method for data recovery in a disabled integrated circuit |
US8060453B2 (en) * | 2008-12-31 | 2011-11-15 | Pitney Bowes Inc. | System and method for funds recovery from an integrated postal security device |
US8095700B2 (en) | 2009-05-15 | 2012-01-10 | Lsi Corporation | Controller and method for statistical allocation of multichannel direct memory access bandwidth |
CN105959215B (en) * | 2016-06-23 | 2019-02-26 | 中国电子科技集团公司第五十四研究所 | A kind of method of communication gate hardware reconfiguration |
CN107678769B (en) * | 2017-09-13 | 2020-07-17 | 湖南斯北图科技有限公司 | SRAM type FPGA anti-radiation reinforced file generation method |
GB2567215B (en) * | 2017-10-06 | 2020-04-01 | Advanced Risc Mach Ltd | Reconfigurable circuit architecture |
US10943652B2 (en) | 2018-05-22 | 2021-03-09 | The Regents Of The University Of Michigan | Memory processing unit |
CN111506519B (en) * | 2020-04-22 | 2021-04-27 | 上海安路信息科技股份有限公司 | Method and system for distributing SRAM unit for FPGA code point |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5693570A (en) * | 1994-10-17 | 1997-12-02 | Sandisk Corporation | Process for manufacturing a programmable power generation circuit for flash EEPROM memory systems |
US5982368A (en) * | 1997-08-26 | 1999-11-09 | Lear Automotive Dearborn, Inc. | Vehicle display using icons |
US6272584B1 (en) * | 1998-09-10 | 2001-08-07 | Compaq Computer Corporation | System board with consolidated EEPROM module |
US6311273B1 (en) * | 1997-02-13 | 2001-10-30 | Walter A. Helbig, Sr. | Method and apparatus for enhancing computer system security |
US20020060336A1 (en) * | 2000-11-23 | 2002-05-23 | Jew-Yong Kuo | Voltage stabilizer of embedded flash memory |
US6467009B1 (en) * | 1998-10-14 | 2002-10-15 | Triscend Corporation | Configurable processor system unit |
US6662314B1 (en) * | 1999-11-15 | 2003-12-09 | Mitsubishi Denki Kabushiki Kaisha | Microcomputer including program for rewriting data in an internal flash memory |
US6720968B1 (en) * | 1998-12-11 | 2004-04-13 | National Instruments Corporation | Video acquisition system including a virtual dual ported memory with adaptive bandwidth allocation |
US6845276B2 (en) * | 2001-06-29 | 2005-01-18 | Electro Scientific Industries | Multiple axis modular controller and method of operating same |
US6938177B1 (en) * | 2001-12-19 | 2005-08-30 | Sentient Sensors Llc | Multi-chip module smart controller |
-
2003
- 2003-01-31 EP EP03425054A patent/EP1443417A1/en not_active Withdrawn
-
2004
- 2004-01-30 US US10/768,401 patent/US7360068B2/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5693570A (en) * | 1994-10-17 | 1997-12-02 | Sandisk Corporation | Process for manufacturing a programmable power generation circuit for flash EEPROM memory systems |
US6311273B1 (en) * | 1997-02-13 | 2001-10-30 | Walter A. Helbig, Sr. | Method and apparatus for enhancing computer system security |
US5982368A (en) * | 1997-08-26 | 1999-11-09 | Lear Automotive Dearborn, Inc. | Vehicle display using icons |
US6272584B1 (en) * | 1998-09-10 | 2001-08-07 | Compaq Computer Corporation | System board with consolidated EEPROM module |
US6467009B1 (en) * | 1998-10-14 | 2002-10-15 | Triscend Corporation | Configurable processor system unit |
US6720968B1 (en) * | 1998-12-11 | 2004-04-13 | National Instruments Corporation | Video acquisition system including a virtual dual ported memory with adaptive bandwidth allocation |
US6662314B1 (en) * | 1999-11-15 | 2003-12-09 | Mitsubishi Denki Kabushiki Kaisha | Microcomputer including program for rewriting data in an internal flash memory |
US20020060336A1 (en) * | 2000-11-23 | 2002-05-23 | Jew-Yong Kuo | Voltage stabilizer of embedded flash memory |
US6845276B2 (en) * | 2001-06-29 | 2005-01-18 | Electro Scientific Industries | Multiple axis modular controller and method of operating same |
US6938177B1 (en) * | 2001-12-19 | 2005-08-30 | Sentient Sensors Llc | Multi-chip module smart controller |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090144461A1 (en) * | 2006-07-03 | 2009-06-04 | Alexander Lampe | Method and system for configuration of a hardware peripheral |
WO2008004158A1 (en) * | 2006-07-03 | 2008-01-10 | Nxp B.V. | Method and system for configuration of a hardware peripheral |
US9720386B2 (en) * | 2010-07-05 | 2017-08-01 | Endress + Hauser Gmbh + Co. Kg | Field device for determining or monitoring a physical or chemical, process variable |
US20120004860A1 (en) * | 2010-07-05 | 2012-01-05 | Endress + Hauser Gmbh + Co. Kg | Field device for determining or monitoring a physical or chemical, process variable |
US8612789B2 (en) | 2011-01-13 | 2013-12-17 | Xilinx, Inc. | Power management within an integrated circuit |
WO2012118586A1 (en) * | 2011-02-28 | 2012-09-07 | Xilinx, Inc. | Integrated circuit with programmable circuitry and an embedded processor system |
KR101496072B1 (en) | 2011-02-28 | 2015-02-25 | 자일링크스 인코포레이티드 | Integrated circuit with programmable circuitry and an embedded processor system |
US9454498B1 (en) | 2011-02-28 | 2016-09-27 | Xilinx, Inc. | Integrated circuit with programmable circuitry and an embedded processor system |
US8667192B2 (en) | 2011-02-28 | 2014-03-04 | Xilinx, Inc. | Integrated circuit with programmable circuitry and an embedded processor system |
CN106648507A (en) * | 2016-12-05 | 2017-05-10 | 中国航空工业集团公司洛阳电光设备研究所 | Circuit and method used for extended DVI display output of embedded processor |
US10963268B1 (en) | 2017-04-18 | 2021-03-30 | Amazon Technologies, Inc. | Interception of identifier indicative of client configurable hardware logic and configuration data |
US10963001B1 (en) * | 2017-04-18 | 2021-03-30 | Amazon Technologies, Inc. | Client configurable hardware logic and corresponding hardware clock metadata |
US11316733B1 (en) | 2017-04-18 | 2022-04-26 | Amazon Technologies, Inc. | Client configurable hardware logic and corresponding signature |
US11226914B2 (en) * | 2017-09-14 | 2022-01-18 | Samsung Electronics Co., Ltd. | Heterogeneous accelerator for highly efficient learning systems |
US11921656B2 (en) | 2017-09-14 | 2024-03-05 | Samsung Electronics Co., Ltd. | Heterogeneous accelerator for highly efficient learning systems |
Also Published As
Publication number | Publication date |
---|---|
US7360068B2 (en) | 2008-04-15 |
EP1443417A1 (en) | 2004-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7360068B2 (en) | Reconfigurable signal processing IC with an embedded flash memory device | |
US6052773A (en) | DPGA-coupled microprocessors | |
US20180067896A1 (en) | Multi-processor with selectively interconnected memory units | |
US7200735B2 (en) | High-performance hybrid processor with configurable execution units | |
US6467009B1 (en) | Configurable processor system unit | |
KR100349787B1 (en) | Single chip microcomputer | |
US20090144485A1 (en) | Process for automatic dynamic reloading of data flow processors (dfps) and units with two- or three-dimensional programmable cell architectures (fpgas, dpgas, and the like) | |
EP2372530A1 (en) | Data processing method and device | |
Tehre et al. | Survey on coarse grained reconfigurable architectures | |
CN105468568B (en) | Efficient coarseness restructurable computing system | |
US7225319B2 (en) | Digital architecture for reconfigurable computing in digital signal processing | |
EP1443519B1 (en) | Embeddable flash memory system for non-volatile storage of code, data and bit-streams for embedded FPGA configurations | |
CN101313290A (en) | Performing an n-bit write access to an mxn-bit-only peripheral | |
EP1290546B1 (en) | Programmable single-chip device and related development environment | |
KR20080083417A (en) | Configuration cache capable low power consumption and reconfigurable processing system including the configuration cache therein | |
US20040248353A1 (en) | Processor and semiconductor integrated circuit | |
CN1707403A (en) | Input and output interface controller | |
KR0184633B1 (en) | Cpu core suitable for a single-chip microcomputer | |
Butts et al. | Reconfigurable work farms on a massively parallel processor array | |
Borgatti et al. | A 1 GOPS reconfigurable signal processing IC with embedded FPGA and 3-port 1.2 GB/s flash memory subsystem | |
Krikelis et al. | A programmable processor with 4096 processing units for media applications | |
Borgatti et al. | A reconfigurable signal processing ic with embedded fpga and multi-port flash memory | |
Williams et al. | Programmable parallel coprocessor architectures for reconfigurable system-on-chip | |
Tsao et al. | Hardware nested looping of parameterized and embedded DSP core | |
Izawa et al. | A Co-Processor Design for an Energy Efficient Reconfigurable Accelerator CMA |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: STMICROELECTRONICS S.R.L., ITALY Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BORGATTI, MICHELE;CALI, LORENZO;LERTORA, FRANCESCO;AND OTHERS;REEL/FRAME:015556/0556;SIGNING DATES FROM 20040214 TO 20040217 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
CC | Certificate of correction | ||
FPAY | Fee payment |
Year of fee payment: 4 |
|
FPAY | Fee payment |
Year of fee payment: 8 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 12TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1553); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 12 |